Anomaly Chicken Cell Identification Using Deep Learning Techniques

Abstract

Chicken cell abnormal identification by manual method that clearly lacks speed and accuracy. However, the success of deep learning techniques from the convolutional neural network (CNN), it may be providing solutions to cell biology laboratory tasks. This paper collected the novel chicken cell microscopic image datasets for training the different kinds of CNN models and optimizers to find promising applications that might be developed. The top model indicates that ResNet34 with Adam optimizer achieved training accuracy of 100%, testing accuracy of 98.14%, and the lower time on the outstanding confusion matrix. In addition, the validation result represented correct identification, guaranteeing by experts. This study shows the potential method to be improved to an application of identification systems in the actual animal and biology laboratories.